Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 24078
    Prev
    Next
    INDEX
    Explanations

    mentions of achievements or significant events

    oai_token-act-pair · gpt-3.5-turbo

    elements related to sports dynamics and team relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )",
    -0.75
    UK
    -0.75
     ®
    -0.74
    chin
    -0.74
    CHQ
    -0.73
    counter
    -0.73
     authorised
    -0.71
     organise
    -0.70
     organised
    -0.70
    bil
    -0.69
    POSITIVE LOGITS
     offseason
    1.54
     coaching
    1.33
     postseason
    1.25
     NBA
    1.21
     Belichick
    1.21
     ESPN
    1.21
     quarterback
    1.19
     coaches
    1.18
     preseason
    1.18
     Harbaugh
    1.18
    Activations Density 1.182%

    No Known Activations